public static class RnnLossLayer.Builder extends BaseOutputLayer.Builder<RnnLossLayer.Builder>
lossFnnIn, nOutactivationFn, biasInit, biasUpdater, gainInit, gradientNormalization, gradientNormalizationThreshold, iupdater, regularization, regularizationBias, weightInitFn, weightNoiseallParamConstraints, biasConstraints, iDropout, layerName, weightConstraints| Constructor and Description |
|---|
Builder() |
Builder(ILossFunction lossFunction) |
Builder(LossFunctions.LossFunction lossFunction) |
| Modifier and Type | Method and Description |
|---|---|
RnnLossLayer |
build() |
RnnLossLayer.Builder |
dataFormat(RNNFormat rnnDataFormat) |
RnnLossLayer.Builder |
nIn(int nIn)
Number of inputs for the layer (usually the size of the last layer).
|
RnnLossLayer.Builder |
nOut(int nOut)
Number of outputs - used to set the layer size (number of units/nodes for the current layer).
|
void |
setNIn(long nIn) |
void |
setNOut(long nOut) |
hasBias, lossFunction, lossFunctionnIn, nOut, unitsactivation, activation, biasInit, biasUpdater, dist, gainInit, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, regularization, regularizationBias, updater, updater, weightDecay, weightDecay, weightDecayBias, weightDecayBias, weightInit, weightInit, weightInit, weightNoiseconstrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, namepublic Builder()
public Builder(LossFunctions.LossFunction lossFunction)
lossFunction - Loss function for the loss layerpublic Builder(ILossFunction lossFunction)
lossFunction - Loss function for the loss layerpublic RnnLossLayer.Builder nIn(int nIn)
FeedForwardLayer.BuildernIn in class FeedForwardLayer.Builder<RnnLossLayer.Builder>nIn - Number of inputs for the layerpublic RnnLossLayer.Builder nOut(int nOut)
FeedForwardLayer.BuilderFeedForwardLayer.Builder.units(int)nOut in class FeedForwardLayer.Builder<RnnLossLayer.Builder>nOut - Number of outputs / layer sizepublic void setNIn(long nIn)
public void setNOut(long nOut)
public RnnLossLayer.Builder dataFormat(RNNFormat rnnDataFormat)
rnnDataFormat - Data format expected by the layer. NCW = [miniBatchSize, size, timeSeriesLength],
NWC = [miniBatchSize, timeSeriesLength, size]. Defaults to NCW.public RnnLossLayer build()
build in class Layer.Builder<RnnLossLayer.Builder>Copyright © 2021. All rights reserved.